Real-time construction worker posture analysis for ergonomics training

Construction activities performed by workers are usually repetitive and physically demanding. Execution of such tasks in awkward postures can strain their body parts and can result in fatigue, injuries or in severe cases permanent disabilities. In view of this, it is essential to train workers, before the commencement of any construction activity. Furthermore, traditional worker monitoring methods are tedious, inefficient and are carried out manually whereas, an automated approach, apart from monitoring, can yield valuable information concerning work-related behavior of worker that can be beneficial for worker training in a virtual reality world. Our research work focuses on developing an automated approach for posture estimation and classification using a range camera for posture analysis and categorizing it as ergonomic or non-ergonomic. Using a range camera, first we classify worker's pose to determine whether a worker is 'standing', 'bending', 'sitting', or 'crawling' and then estimate the posture of the worker using OpenNI middleware to get the body joint angles and spatial locations. A predefined set of rules is then formulated to use this body posture information to categorize tasks as ergonomic or non-ergonomic.

[1]  Harald Wuest,et al.  Linear-projection-based classification of human postures in time-of-flight data , 2009, 2009 IEEE International Conference on Systems, Man and Cybernetics.

[2]  Jimmie Hinze,et al.  Autonomous pro-active real-time construction worker and equipment operator proximity safety alert system , 2010 .

[3]  Carlos H. Caldas,et al.  Real-Time Three-Dimensional Occupancy Grid Modeling for the Detection and Tracking of Construction Resources , 2007 .

[4]  Nooritawati Md. Tahir,et al.  Analysis of PCA based feature vectors for SVM posture classification , 2010, 2010 6th International Colloquium on Signal Processing & its Applications.

[5]  Jochen Teizer,et al.  Human Motion Analysis Using 3D Range Imaging Technology , 2009 .

[6]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[7]  Gary A. Mirka,et al.  Accuracy of a three-dimensional lumbar motion monitor for recording dynamic trunk motion characteristics , 1992 .

[8]  Maury A Nussbaum,et al.  Fatigue during prolonged intermittent overhead work: reliability of measures and effects of working height , 2007, Ergonomics.

[9]  Maury A. Nussbaum,et al.  Low back injury risks during construction with prefabricated (panelised) walls: effects of task and design factors , 2011, Ergonomics.

[10]  Abdullatif Alwasel,et al.  Sensing Construction Work-Related Musculoskeletal Disorders (WMSDs) , 2011 .

[11]  Cheryl Fairfield Estill,et al.  Simple solutions; ergonomics for construction workers , 2007 .

[12]  Jochen Teizer,et al.  Range Imaging as Emerging Optical Three-Dimension Measurement Technology , 2007 .

[13]  Ahmed M. Elgammal,et al.  The Role of Manifold Learning in Human Motion Analysis , 2006, Human Motion.

[14]  Wanqing Li,et al.  Kernel PCA of HOG features for posture detection , 2009, 2009 24th International Conference Image and Vision Computing New Zealand.

[15]  Giovanni C. Migliaccio,et al.  Wearable physiological status monitors for measuring and evaluating workers physical strain: Prelim , 2011 .

[16]  Carlos H. Caldas,et al.  Framework for Real-Time Three-Dimensional Modeling of Infrastructure , 2005 .

[17]  Jochen Teizer.  3D range imaging camera sensing for active safety in construction , 2008, J. Inf. Technol. Constr..

[18]  Koshy Varghese,et al.  Video Annotation Framework for Accelerometer Placement in Worker Activity Recognition Studies , 2011 .